s390: add support for DCACHE_WORD_ACCESS

Implement load_unaligned_zeropad() and enable DCACHE_WORD_ACCESS to
speed up string operations in fs/dcache.c and fs/namei.c.

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>

4 files changed, 45 insertions, 0 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index ae29e4392664..b0d67ac8695f 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -131,6 +131,7 @@ config S390
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
 	select BUILDTIME_TABLE_SORT
 	select CLONE_BACKWARDS2
+	select DCACHE_WORD_ACCESS if !KMSAN
 	select DMA_OPS if PCI
 	select DYNAMIC_FTRACE if FUNCTION_TRACER
 	select FUNCTION_ALIGNMENT_8B if CC_IS_GCC
diff --git a/arch/s390/include/asm/asm-extable.h b/arch/s390/include/asm/asm-extable.h
index d1ecc2b6e5d3..4a6b0a8b6412 100644
--- a/arch/s390/include/asm/asm-extable.h
+++ b/arch/s390/include/asm/asm-extable.h
@@ -13,6 +13,7 @@
 #define EX_TYPE_UA_LOAD_MEM	4
 #define EX_TYPE_UA_LOAD_REG	5
 #define EX_TYPE_UA_LOAD_REGPAIR	6
+#define EX_TYPE_ZEROPAD		7
 
 #define EX_DATA_REG_ERR_SHIFT	0
 #define EX_DATA_REG_ERR		GENMASK(3, 0)
@@ -80,4 +81,7 @@
 #define EX_TABLE_UA_LOAD_REGPAIR(_fault, _target, _regerr, _regzero)	\
 	__EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_REGPAIR, _regerr, _regzero, 0)
 
+#define EX_TABLE_ZEROPAD(_fault, _target, _regdata, _regaddr)		\
+	__EX_TABLE(__ex_table, _fault, _target, EX_TYPE_ZEROPAD, _regdata, _regaddr, 0)
+
 #endif /* __ASM_EXTABLE_H */
diff --git a/arch/s390/include/asm/word-at-a-time.h b/arch/s390/include/asm/word-at-a-time.h
index 09b37541a175..2579f1694b82 100644
--- a/arch/s390/include/asm/word-at-a-time.h
+++ b/arch/s390/include/asm/word-at-a-time.h
@@ -3,6 +3,7 @@
 #define _ASM_WORD_AT_A_TIME_H
 
 #include <linux/kernel.h>
+#include <asm/asm-extable.h>
 #include <asm/bitsperlong.h>
 
 struct word_at_a_time {
@@ -39,4 +40,25 @@ static inline unsigned long zero_bytemask(unsigned long data)
 	return ~1UL << data;
 }
 
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long data;
+
+	asm volatile(
+		"0:	lg	%[data],0(%[addr])\n"
+		"1:	nopr	%%r7\n"
+		EX_TABLE_ZEROPAD(0b, 1b, %[data], %[addr])
+		EX_TABLE_ZEROPAD(1b, 1b, %[data], %[addr])
+		: [data] "=d" (data)
+		: [addr] "a" (addr), "m" (*(unsigned long *)addr));
+	return data;
+}
+
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/s390/mm/extable.c b/arch/s390/mm/extable.c
index fe87291df95d..0a0738a473af 100644
--- a/arch/s390/mm/extable.c
+++ b/arch/s390/mm/extable.c
@@ -61,6 +61,22 @@ static bool ex_handler_ua_load_reg(const struct exception_table_entry *ex,
 	return true;
 }
 
+static bool ex_handler_zeropad(const struct exception_table_entry *ex, struct pt_regs *regs)
+{
+	unsigned int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data);
+	unsigned int reg_data = FIELD_GET(EX_DATA_REG_ERR, ex->data);
+	unsigned long data, addr, offset;
+
+	addr = regs->gprs[reg_addr];
+	offset = addr & (sizeof(unsigned long) - 1);
+	addr &= ~(sizeof(unsigned long) - 1);
+	data = *(unsigned long *)addr;
+	data <<= BITS_PER_BYTE * offset;
+	regs->gprs[reg_data] = data;
+	regs->psw.addr = extable_fixup(ex);
+	return true;
+}
+
 bool fixup_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *ex;
@@ -81,6 +97,8 @@ bool fixup_exception(struct pt_regs *regs)
 		return ex_handler_ua_load_reg(ex, false, regs);
 	case EX_TYPE_UA_LOAD_REGPAIR:
 		return ex_handler_ua_load_reg(ex, true, regs);
+	case EX_TYPE_ZEROPAD:
+		return ex_handler_zeropad(ex, regs);
 	}
 	panic("invalid exception table entry");
 }